Unlock instant, AI-driven research and patent intelligence for your innovation.

Identification method of traffic high-risk personnel based on gradient boosting decision tree algorithm

A person identification and decision tree technology, applied in the field of high-risk traffic person identification, can solve problems such as lack of application, achieve the effect of short parameter adjustment time, ensure accuracy, and improve model accuracy

Active Publication Date: 2021-09-17
JIANGSU ZHITONG TRANSPORTATION TECH
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The Gradient Boosting Decision Tree (GDBT) algorithm achieves the purpose of classifying or regressing data by using an additive model and continuously reducing the residual error generated during the training process. It is the best fit for the real distribution in the traditional machine learning algorithm. One of several algorithms, applying it to the processing of traffic violation data can dig out valuable traffic safety information, but there is still a lack of such applications

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Identification method of traffic high-risk personnel based on gradient boosting decision tree algorithm
  • Identification method of traffic high-risk personnel based on gradient boosting decision tree algorithm
  • Identification method of traffic high-risk personnel based on gradient boosting decision tree algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0047] A method for identifying high-risk persons in traffic based on a gradient boosting decision tree algorithm, extracts the characteristic attributes of traffic participants' safety behavior from traffic violation records and trains a model to realize high-risk person identification and safety risk prediction; such as figure 1 , the specific method flow is:

[0048] S1. Based on the original traffic violation data and accident data, construct an illegal data set, a serious accident data set, and a minor accident data set.

[0049] In the embodiment, the original traffic violation data and accident data in step S1 include relevant personnel certificate information; the illegal data set is obtained after preprocessing operations such as collection and classification of the original illegal records; the illegal data set is the full sample data of personnel illegal records. , the data set information includes the personnel certificate number, the number of violations, the type...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a method for identifying high-risk persons in traffic based on a gradient-lifting decision tree algorithm. Based on the original traffic violation data and accident data, the gradient-lifting decision tree algorithm is used to train and correct the high-risk person identification model, and the information on the illegal attributes of personnel is input into the model. , it can realize the identification and prediction of high-risk personnel, which has practical significance for improving the efficiency of traffic safety management and assisting the daily safety management of traffic police to be more targeted and proactive.

Description

technical field [0001] The invention relates to a method for identifying traffic high-risk persons based on a gradient boosting decision tree algorithm. Background technique [0002] Research in the field of road traffic safety mostly focuses on the analysis of the correlation law between external factors such as the environment, road infrastructure, and traffic flow operation status and traffic accidents, such as Chinese patents CN201710400521. Distribution characteristics, or analyze the regular characteristics of traffic accidents from the perspective of environment, traffic control measures and other characteristics. Internal factors such as the behaviors and habits of traffic participants (motor vehicles, non-motor vehicle drivers, and pedestrians) themselves lack in-depth research and analysis due to their wide information dimensions and limited information perception methods. The impact of accidents is an inevitable content of traffic safety research, and has great p...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06F16/2458
CPCG06F18/214
Inventor 吕伟韬刘林陈凝饶欢
Owner JIANGSU ZHITONG TRANSPORTATION TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com